Presentation 2013-02-18
Super resolution without reference images based on combination of high frequency components using total variation regularization
Hiroki TSURUSAKI, Masashi KAMEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to improve the image quality of enlarged image, the super resolution using total variation(TV) regularization has been proposed. However, the previous method without reference images has a problem that the edge distortion such as blur is occurred in the enlarged image because higher frequency information isn't able to be estimated accurately. This paper presents new super resolution based on TV regularization that calculates two kinds of higher frequency components with edge and texture, and composes the higher frequency image by combining both components appropriately. It is seen in the experimental results that the enlarged image by the proposed method decreases the blur around edge compared with the previous method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Super Resolution / Total Variation Regularization / Hybrid Texture Image / Bicubic Interpolation
Paper # ITS2012-40,IE2012-120
Date of Issue

Conference Information
Committee IE
Conference Date 2013/2/11(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Super resolution without reference images based on combination of high frequency components using total variation regularization
Sub Title (in English)
Keyword(1) Super Resolution
Keyword(2) Total Variation Regularization
Keyword(3) Hybrid Texture Image
Keyword(4) Bicubic Interpolation
1st Author's Name Hiroki TSURUSAKI
1st Author's Affiliation Faculty of Software and Information Science, Iwate Prefectural University()
2nd Author's Name Masashi KAMEDA
2nd Author's Affiliation Faculty of Software and Information Science, Iwate Prefectural University
Date 2013-02-18
Paper # ITS2012-40,IE2012-120
Volume (vol) vol.112
Number (no) 434
Page pp.pp.-
#Pages 6
Date of Issue